Multifractal Analysis of the Impact of Fuel Cell Introduction in the Korean Electricity Market DOI Creative Commons

Seung Eun Ock,

Minhyuk Lee, Jae Wook Song

et al.

Fractal and Fractional, Journal Year: 2024, Volume and Issue: 8(10), P. 573 - 573

Published: Sept. 30, 2024

This study employs multifractal detrended fluctuation analysis to investigate the impact of fuel cell introduction in Korean electricity market via lens scaling behavior. Using analysis, research delineates discrepancies between peak and off-peak hours, accounting for daily cyclicity market, proposes a crossover point detection method based on Chow test. Furthermore, impacts are evidenced through various methods that encompass spectra efficiency. The findings initially indicate higher degree multifractality during hours relative hours. In particular, points emerged solely unveiling short- long-term dynamics predicated near-annual cycle. Additionally, average Hurst exponent short-term was 0.542, while 0.098, representing notable discrepancy. cells attenuated heterogeneity behavior, which is potentially attributable decreased volatility both supply demand spectra. Remarkably, after cells, there discernible decrease influence long-range correlation within multifractality, exhibited an increased propensity toward random-walk phenomenon also detected deficiency measure, from 0.536, prior introduction, 0.267, following signifying improvement implies into engendered stability consistent increase demand, mitigating sides, thus increasing

Language: Английский

Electricity price forecast on day-ahead market for mid- and short terms: capturing spikes in data sequences using recurrent neural network techniques DOI
Adela Bârã, Simona‐Vasilica Oprea

Electrical Engineering, Journal Year: 2024, Volume and Issue: 106(5), P. 6309 - 6338

Published: April 11, 2024

Language: Английский

Citations

5
Electricity Price Forecasting in the Irish Balancing Market DOI Creative Commons
Ciaran O’Connor,

Joseph Collins,

Steven Prestwich

et al.

Energy Strategy Reviews, Journal Year: 2024, Volume and Issue: 54, P. 101436 - 101436

Published: June 12, 2024

Short-term electricity markets are becoming more relevant due to less-predictable renewable energy sources, attracting considerable attention from the industry. The balancing market is closest real-time and most volatile among them. Its price forecasting literature limited, inconsistent outdated, with few deep learning attempts no public dataset. This work applies Irish a variety of prediction techniques proven successful in widely studied day-ahead market. We compare statistical, machine learning, models using framework that investigates impact different training sizes. defines hyperparameters calibration settings; dataset made ensure reproducibility be used as benchmarks for future works. An extensive numerical study shows well-performing do not perform well one, highlighting these fundamentally constructs. best model LEAR, statistical approach based on LASSO, achieving mean absolute error 32.82 €/MWh, surpassing complex computationally demanding approaches errors ranging 33.71 €/MWh 44.55 €/MWh.

Language: Английский

Citations

5
Short-term electricity price forecasting through demand and renewable generation prediction DOI Creative Commons
E. Belenguer, Jorge Segarra-Tamarit, Emilio Pérez

et al.

Mathematics and Computers in Simulation, Journal Year: 2024, Volume and Issue: 229, P. 350 - 361

Published: Oct. 10, 2024

Language: Английский

Citations

4
A Multi-Output Ensemble Learning Approach for Multi-Day Ahead Index Price Forecasting DOI Creative Commons
Kartik Sahoo, Manoj Thakur

AppliedMath, Journal Year: 2025, Volume and Issue: 5(1), P. 6 - 6

Published: Jan. 10, 2025

The stock market index future price forecasting is one of the imperative financial time series problems. Accurately estimated closing prices can play important role in making trading decisions and investment plannings. This work proposes a new multi-output ensemble framework that integrates hybrid systems generated through importance score based feature weighted learning models continuous multi-colony ant colony optimization technique (MACO-LD) for multi-day ahead forecasting. Importance scores are obtained four different generation strategies (F-test, Relief, Random Forest, Grey correlation). Multi-output variants three baseline algorithms brought to address study uses namely least square support vector regression (MO-LSSVR), proximal (MO-PSVR) ε-twin (MO-ε-TSVR) as methods models. For purpose an index, comprehensive collection technical indicators has been taken into consideration input features. proposed tested over eight futures explore performance individual predictors after incorporating methods. Finally, algorithm employed construct results from along with algorithms. experimental all established exhibits superior compared

Language: Английский

Citations

0
THE UTILITY OF MACHINE LEARNING IN THE ANALYSIS OF THE CLEAN ENERGY TRANSITION: THE CASE OF GERMANY DOI Creative Commons
Tomislav Gelo, Marko Družić

Ekonomska misao i praksa, Journal Year: 2025, Volume and Issue: Online First(Online First), P. 1 - 19

Published: Jan. 17, 2025

One of the main components clean energy transition process in EU are its liberalized electricity markets.Since most is traded day-ahead closed auctions, reliable and accurate price prediction has become a question paramount importance.This led to extensive use machine learning algorithms, which have increasingly powerful last decade, predicting movement key economic variables sector.However, their currently for part limited producing black-box predictions, with no attempt produce explanations or insight.The purpose this paper see whether bridge can be built between disconnected realms analysis learning.We decision tree-based techniques analyse variability hourly prices German market from 2015-2020.We then compare results coefficient magnitudes linear regression framework.Our indicate that two approaches end up substantial agreement on variable importance.We conclude an area worth exploring further, since it lead expanding sector toolkit, could more informed policy.

Language: Английский

Citations

0
A conceptual meta‐level digital twin architecture for energy communities in Romania and other ex‐communist countries DOI Open Access
Simona‐Vasilica Oprea, Adela Bârã

Environmental Progress & Sustainable Energy, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 30, 2025

Abstract In contrast to the prevalent ecological motivations seen in European Energy Communities (ECs), Romania, driving forces behind EC initiatives are somewhat different. Approximately 60% of these primarily focused on addressing energy poverty. The remaining 40% driven by a desire for autonomy. This article explores intricate landscape projects, focusing their role aligning with climate change necessities. We delve into current state industry, identifying critical needs, gaps, and challenges that hinder full potential. Furthermore, we propose potential research directions bridge emphasizing development Meta‐level digital twin (DT) architecture. It aims enhance decision‐making processes simulating systems real‐time responses various scenarios regulatory changes. Then, focus cost‐effectiveness installing PV Romania estimate technical households (12.9 GW) prosumers' installations 2030 2050. To forecast adoption from 2025 2050, proposed model relies several assumptions, such as annual decreases CAPEX 1%, OPEX 0.15%, increment electricity prices 0.1% per year, degradation rate year systems. following projections obtained (3948 MW) 2050 (5265 MW), estimating growth will be 33%.

Language: Английский

Citations

0
Technical Analysis and Machine Learning Applied to the Short-Term Electricity Trading Market: Italian and Brazilian Cases DOI
Raphael Paulo Beal Piovezan, Pedro Paulo de Andrade, Sérgio Luciano Ávila

et al.

Computational Economics, Journal Year: 2025, Volume and Issue: unknown

Published: April 25, 2025

Language: Английский

Citations

0
Charting the BRIC countries’ connection of political stability, economic growth, demographics, renewables and CO2 emissions DOI Creative Commons
Simona‐Vasilica Oprea, Irina Georgescu, Adela Bârã

et al.

Economic Change and Restructuring, Journal Year: 2024, Volume and Issue: 57(5)

Published: Sept. 6, 2024

Language: Английский

Citations

2
Multifractal Analysis of the Impact of Fuel Cell Introduction in the Korean Electricity Market DOI Creative Commons

Seung Eun Ock,

Minhyuk Lee, Jae Wook Song

et al.

Fractal and Fractional, Journal Year: 2024, Volume and Issue: 8(10), P. 573 - 573

Published: Sept. 30, 2024

This study employs multifractal detrended fluctuation analysis to investigate the impact of fuel cell introduction in Korean electricity market via lens scaling behavior. Using analysis, research delineates discrepancies between peak and off-peak hours, accounting for daily cyclicity market, proposes a crossover point detection method based on Chow test. Furthermore, impacts are evidenced through various methods that encompass spectra efficiency. The findings initially indicate higher degree multifractality during hours relative hours. In particular, points emerged solely unveiling short- long-term dynamics predicated near-annual cycle. Additionally, average Hurst exponent short-term was 0.542, while 0.098, representing notable discrepancy. cells attenuated heterogeneity behavior, which is potentially attributable decreased volatility both supply demand spectra. Remarkably, after cells, there discernible decrease influence long-range correlation within multifractality, exhibited an increased propensity toward random-walk phenomenon also detected deficiency measure, from 0.536, prior introduction, 0.267, following signifying improvement implies into engendered stability consistent increase demand, mitigating sides, thus increasing

Language: Английский

Citations

1